# A Lightweight Dual-Mode Optimization for Generative Face Video Coding

arXiv: https://arxiv.org/abs/2508.13547 · HTML: https://mlsanity.com/paper/2508.13547/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 33 references that are in the map.
- First posted on arXiv 19 Aug 2025.

## Builds on (most cited first, 17 of 17)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [VoxCeleb2: Deep Speaker Recognition](https://mlsanity.com/paper/1806.05622/) (2018)
- [Image Quality Assessment: Unifying Structure and Texture Similarity](https://mlsanity.com/paper/2004.07728/) (2020)
- [Learning Efficient Convolutional Networks through Network Slimming](https://mlsanity.com/paper/1708.06519/) (2017)
- [CelebV-HQ: A Large-Scale Video Facial Attributes Dataset](https://mlsanity.com/paper/2207.12393/) (2022)
- [Understanding Straight-Through Estimator in Training Activation Quantized Neural Nets](https://mlsanity.com/paper/1903.05662/) (2019)
- [QuantCache: Adaptive Importance-Guided Quantization with Hierarchical Latent and Layer Caching for Video Generation](https://mlsanity.com/paper/2503.06545/) (2025)
- [Generative Face Video Coding Techniques and Standardization Efforts: A Review](https://mlsanity.com/paper/2311.02649/) (2023)
- [Interactive Face Video Coding: A Generative Compression Framework](https://mlsanity.com/paper/2302.09919/) (2023)
- [Generative Visual Compression: A Review](https://mlsanity.com/paper/2402.02140/) (2024)
- [Standardizing Generative Face Video Compression using Supplemental Enhancement Information](https://mlsanity.com/paper/2410.15105/) (2024)
- [Generative Models at the Frontier of Compression: A Survey on Generative Face Video Coding](https://mlsanity.com/paper/2506.07369/) (2025)

## Abstract (arXiv)

Generative Face Video Coding (GFVC) achieves superior rate-distortion performance by leveraging the strong inference capabilities of deep generative models. However, its practical deployment is hindered by large model parameters and high computational costs. To address this, we propose a lightweight GFVC framework that introduces dual-mode optimization -- combining architectural redesign and operational refinement -- to reduce complexity whilst preserving reconstruction quality. Architecturally, we replace traditional 3 x 3 convolutions with slimmer and more efficient layers, reducing complexity without compromising feature expressiveness. Operationally, we develop a two-stage adaptive channel pruning strategy: (1) soft pruning during training identifies redundant channels via learnable thresholds, and (2) hard pruning permanently eliminates these channels post-training using a derived mask. This dual-phase approach ensures both training stability and inference efficiency. Experimental results demonstrate that the proposed lightweight dual-mode optimization for GFVC can achieve 90.4% parameter reduction and 88.9% computation saving compared to the baseline, whilst achieving superior performance compared to state-of-the-art video coding standard Versatile Video Coding (VVC) in terms of perceptual-level quality metrics. As such, the proposed method is expected to enable efficient GFVC deployment in resource-constrained environments such as mobile edge devices.